blend-ai

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses that the tool modifies an object (implied by 'create a clean topology'), but lacks details on permissions, side effects, or error handling. It partially compensates by explaining mode-specific behavior for 'voxel_size', but overall behavioral context is minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured and concise: a clear purpose sentence followed by organized sections for Args and Returns. Each sentence adds value without redundancy, and information is front-loaded appropriately. No wasted words or unnecessary details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 3 parameters with 0% schema coverage and no annotations, the description does a good job explaining inputs and outputs. It specifies the return format ('Dict with object name and new vertex count'), and while an output schema exists, the description adds clarity. However, it could better address behavioral aspects like error cases or performance implications.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It adds meaningful semantics: 'object_name' is clarified as 'Name of the mesh object to remesh', 'voxel_size' is explained with 'smaller = more detail' and mode dependency, and 'mode' lists valid options. This covers all parameters well, though it could detail default behaviors more.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Remesh an object to create a clean topology.' It specifies the verb ('remesh') and resource ('object'), and while it doesn't explicitly differentiate from siblings like 'subdivide_mesh' or 'bevel_edges', the focus on topology cleaning is reasonably distinct. However, it lacks explicit sibling comparison, preventing a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, such as needing a mesh object, or compare it to similar tools like 'subdivide_mesh' or 'bevel_edges' for topology tasks. Usage is implied only through the description's purpose statement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.